Lack of diversity in advertising is a long-standing problem. Despite growing cultural awareness and missed business opportunities, many minorities remain under- or inappropriately represented in advertising. Previous research has studied how people react to culturally embedded ads, but such work focused mostly on print media or television using lab experiments. In this work, we look at diversity in content posted by 69 U.S. brands on two social media platforms, Instagram and Facebook. Using face detection technology, we infer the gender, race, and age of both the faces in the ads and of the users engaging with ads. Using this dataset, we investigate the following: (1) What type of content brands put out – Is there a lack of diversity?; (2) How does a brand’s content diversity compare to its audience diversity – Is any lack of diversity simply a reflection of the audience?; and (3) How does brand diversity relate to user engagement – Do users of a particular demographic engage more if their demographics are represented in a post?